# ai-dynamo/nixl

> NVIDIA library that accelerates point-to-point data transfers in AI inference frameworks, abstracting over different memory types (CPU, GPU) and storage backends via a plug-in architecture.

- Magnitude: 0.8 out of 10 — Quiet
- Stars: 1,280 total · +1 star today, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: DevOps & infrastructure · Language: C++ · Created: 2025-03-05 · Last push: 2026-09-30
- GitHub: https://github.com/ai-dynamo/nixl · Page: https://gitnova.dev/en/r/ai-dynamo/nixl

## Useful for

- Speed up KV-cache exchange between GPU nodes in distributed inference
- Plug in a storage backend (POSIX, GDS, Azure Blob) for cross-node data transfer
- Run nixlbench to measure point-to-point transfer throughput

## Why it’s here

- 1 star so far today, about 2 expected by the end of the day.
- GitHub Trending C++ today: #13, +1 star.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 458
- Issues and pull requests: 2,310
- Watchers: 27
- Average over the last week: 2 per day
- Usual pace: 2 per day
- Stars in the last hour (measured): 0
- Latest release: v1.5.0 (2026-09-30)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-01 … 2026-09-30: 3, 3, 1, 2, 3, 1, 1, 3, 5, 4, 3, 1, 2, 2, 4, 3, 3, 1, 0, 0, 2, 1, 2, 3, 3, 2, 1, 0, 2, 1

## Spotted in now

- GitHub Trending C++ today: #13, +1 star

## Similar by description

1. **kvcache-ai/Mooncake** — 1.5 · Steady · Language models · C++ · +2 stars today, ≈ 4 by evening
   LLM serving platform built on a KVCache-centric disaggregated architecture: separates prefill and decode and transfers KV cache between nodes over RDMA. Powers Kimi in production at Moonshot AI.
   Full card: https://gitnova.dev/en/r/kvcache-ai/Mooncake.md
2. **microsoft/onnxruntime** — 1.8 · Steady · Language models · C++ · +5 stars today, ≈ 9 by evening
   Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.
   Full card: https://gitnova.dev/en/r/microsoft/onnxruntime.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-30 14:35 UTC, updated every 30 minutes.